Related papers: Evaluating Manual Intervention to Address the Chal…
Solana is rapidly gaining traction among smart contract developers and users. However, its growing adoption has been accompanied by a series of major security incidents, which have spurred research into automated analysis techniques for…
The rise of instruction-tuned Large Language Models (LLMs) marks a significant advancement in artificial intelligence (AI) (tailored to respond to specific prompts). Despite their popularity, applying such models to debug security…
Although language model (LM) agents have demonstrated increased performance in multiple domains, including coding and web-browsing, their success in cybersecurity has been limited. We present EnIGMA, an LM agent for autonomously solving…
Artificial Intelligence has gained a lot of traction in the recent years, with machine learning notably starting to see more applications across a varied range of fields. One specific machine learning application that is of interest to us…
Software vulnerabilities continue to be ubiquitous, even in the era of AI-powered code assistants, advanced static analysis tools, and the adoption of extensive testing frameworks. It has become apparent that we must not simply prevent…
Regression testing ensures that a software system when it evolves still performs correctly and that the changes introduce no unintended side-effects. However, the creation of regression test cases that show divergent behavior needs a lot of…
A promising research direction in enabling LLMs to generate consistently correct code involves addressing their inability to properly estimate program execution, particularly for code they generate. In this work, we demonstrate that Code…
Dynamic analysis, through rehosting, is an important capability for security assessment in embedded systems software. Existing rehosting techniques aim to provide high-fidelity execution by accurately emulating hardware and peripheral…
While CUDA has become a major parallel computing platform and programming model for general-purpose GPU computing, CUDA-induced bug patterns have not yet been well explored. In this paper, we conduct the first empirical study to reveal…
As large language models (LLMs) increasingly integrate native code interpreters, they enable powerful real-time execution capabilities, substantially expanding their utility. However, such integrations introduce potential system-level…
A flaky test yields inconsistent results upon repetition, posing a significant challenge to software developers. An extensive study of their presence and characteristics has been done in classical computer software but not quantum computer…
The autonomous discovery of bugs remains a significant challenge in modern software development. Compared to code generation, the complexity of dynamic runtime environments makes bug discovery considerably harder for large language models…
Due to the increasing size of HPC machines, the fault presence is becoming an eventuality that applications must face. Natively, MPI provides no support for the execution past the detection of a fault, and this is becoming more and more…
Programmable packet processors and P4 as a programming language for such devices have gained significant interest, because their flexibility enables rapid development of a diverse set of applications that work at line rate. However, this…
Modern agentic frameworks (e.g., CrewAI and AutoGen) have evolved into complex, autonomous multi-agent systems, introducing unique reliability challenges beyond earlier pipeline-based LLM libraries. However, existing empirical studies focus…
Tile-based programming frameworks are increasingly adopted to write high-performance GPU kernels in domains such as deep learning and scientific computing. While these frameworks enhance productivity and hardware utilization, their…
The sudden emergence of large language models (LLMs) such as ChatGPT has had a disruptive impact throughout the computing education community. LLMs have been shown to excel at producing correct code to CS1 and CS2 problems, and can even act…
We introduce a novel copy-protection method for industrial control software. With our method, a program executes correctly only on its target hardware and behaves differently on other machines. The hardware-software binding is based on…
The iterative and incremental nature of software development using models typically makes a model of a system incomplete (i.e., partial) until a more advanced and complete stage of development is reached. Existing model execution approaches…
Maintaining reliable UI test suites in large-scale enterprise applications is a persistent and costly challenge. We present an industrial case study of a multi-agent autonomous testing system evaluated using anonymized execution data from a…